Amity School of Engineering & Technology
Session 2:
Schema Theory
By
Dr. Ashok Kumar
Amity School of Engineering & Technology
•Introduction to Schema Theory
• Definition: Schema theory refers to the mental frameworks that help
individuals or systems organize and interpret information.
Core Concepts of Schema Theory
• A schema is a structured cluster of concepts, events, and actions that are
used to process information.
• In humans, schemas are formed based on past experiences and are used
to predict future behavior or outcomes.
•How Schemas Work
• Assimilation: The process of integrating new experiences into existing
schemas.
• Accommodation: Adjusting existing schemas when new information
doesn't fit.
Amity School of Engineering & Technology
schema- is used in cognitive science to refer to
a particular organized way of perceiving
cognitively and responding to a complex
situation.
• is generic, equivalent to an object in OOP: can
encapsulate 2 types of knowledge:
– schema specific knowledge (local data)
– procedural knowledge (methods)
• schema instantation is specific to a situation,
equivalent to an instance in OOP
3
• A schema can be composed of other schemas
Amity School of Engineering & Technology
Behaviors and schema theory
A behavior is a schema which is composed of a
motor schema and a perceptual schema.
The motor schema represents the template
for the physical activity
The perceptual schema embodies the
sensing.
4
Amity School of Engineering & Technology
Behaviors and schema theory
The motor schema and perceptual schema are like pieces of a
puzzle; both pieces
5
must be together in place before there is a behavior.
Amity School of Engineering & Technology
Where are the Schemas/Objects in
B(S)=R?
S=Prey R= snap
Feeding
BEHAVIOR
Pattern of Pattern
Sensory of Motor
Input Actions
Stimulus-response (SR) diagrams
Amity School of Engineering & Technology
Perceptual Schema
S=Prey R= snap
Feeding
BEHAVIOR
Pattern of Pattern
Sensory of Motor
Input Actions
Perceptual
Schema
Amity School of Engineering & Technology
Motor Schema
S=Prey R= snap
Feeding
BEHAVIOR
Pattern of Pattern
Sensory of Motor
Input Actions
Perceptual Motor
Schema Schema
Amity School of Engineering & Technology
Behavioral Schema= PS+MS
S=Prey R= snap
Feeding
BEHAVIOR
Pattern of Pattern
Sensory of Motor
Input Actions
Perceptual Motor
Schema Schema
Behavioral
Schema
Amity School of Engineering & Technology
Behaviors and schema theory- Schema
architecture
• Schema is a pattern of action, a basic unit of action from
which complex actions are constructed
• Two kinds of schemas
Motor schemas and
Perceptual schemas
• A schema stores both how to react and the way that reaction
can be realized
• Provides a language for connecting action and perception
• Activation levels are associated with schemas that determine their
10
Amity School of Engineering & Technology
Behaviors and schema theory- Perceptual And
Motor Schemas
• A perceptual schema embodies the process whereby the system
determines whether a given domain of interaction is present in the
environment.
• A schema assemblage combines an estimate of environmental
state with a representation of goals and needs
• The internal state is also updated by knowledge of the state of
execution of current plans made up of motor schemas
• which are similar to control systems but distinguished by the fact
11
that they can be combined to form coordinated control programs
Amity School of Engineering & Technology
Behavioral Schema is made up of 2 schemas
percept,
Perceptual strength Motor
Schema Schema
sensor (PS) (MS) Action,
gain
Behaviors must have a PS and MS, though 1 can be NULL
Reflexive behaviors usually just have “methods”, not data
12
Amity School of Engineering & Technology
2 Parts of a Schema
Behavior-specific knowledge
data
Methods
percept,
(2) Perceptual strength Motor
Schema Schema
sensor (PS) (MS) Action,
gain
Behavior specific knowledge can be timers, logic
for instantiating the appropriate perceptual
13
schema, etc.
Amity School of Engineering & Technology
Behavioral coordination: action selection
14
Amity School of Engineering & Technology
• Schema Application in Robotics
• Autonomous Navigation:
• Perceptual schemas define how the robot senses its surroundings (e.g.,
detecting obstacles).
• Behavioral schemas handle the robot's movement (e.g., moving forward,
avoiding obstacles).
• Reactive Agents:
• AI agents in games use schemas to react to player actions.
• Schemas categorize the player's behaviors and trigger appropriate
responses (e.g., defense or attack).
Amity School of Engineering & Technology
• Advantages of Schema Theory in Reactive Systems
• Simplified Decision-Making:
• The use of schemas allows for fast and efficient decision-making.
• Real-Time Adaptation:
• The system can quickly accommodate new stimuli by assimilating them
into existing schemas or adjusting schemas as needed.
• Scalability:
• Schema-based systems can scale well as more schemas are added
without drastically increasing system complexity.
Amity School of Engineering & Technology
• Limitations of Schema Theory in Reactive Paradigm
• Rigidity in Complex Environments:
• Schema-based systems may struggle with entirely novel situations or
complex environments that don't fit pre-programmed schemas.
• Limited Learning Capabilities:
• Schemas depend on prior knowledge, so the system may be unable to
handle scenarios that it hasn't encountered before.
• Difficulty in Updating:
• Updating schemas in real-time can be challenging if the system
encounters conflicting information or needs rapid accommodation.
Amity School of Engineering & Technology
• Case Study - Schema-Based Reactive Robot
• Scenario:
• A robot uses a set of perceptual schemas to detect various objects in its
environment (e.g., furniture, walls, humans).
• Behavioral schemas guide its responses: when it perceives a human, it
stops and greets them; when it detects an obstacle, it turns.
• Process:
• Perceptual Schema: Identifies object type and proximity.
• Behavioral Schema: Matches perceptual input to the corresponding
behavior (e.g., stop, greet, turn).
• Outcomes:
• The robot efficiently navigates through the environment without requiring a
complex decision-making system.